© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 6909
    Prev
    Next
    INDEX
    Explanations

    phrases or acronyms related to Washington D.C

    oai_token-act-pair · gpt-3.5-turbo

    sentences related to legal or governmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.78
    VALUE
    -0.75
    quel
    -0.71
     contrace
    -0.70
    ãĥı
    -0.69
    ebook
    -0.66
    zees
    -0.65
    enstein
    -0.65
    cient
    -0.64
    pring
    -0.64
    POSITIVE LOGITS
     Residents
    0.86
     Superior
    0.81
     City
    0.80
    area
    0.79
     County
    0.79
     Utilities
    0.78
     skyline
    0.76
     resident
    0.76
     Customs
    0.73
     Liberties
    0.73
    Activations Density 0.038%

    No Known Activations